More Like this

1. Continuous Time Analysis of Momentum Methods

   Kovachki, Nikola ; Stuart, Andrew M. ( January 2021 , Journal of machine learning research)

   null (Ed.)

   Gradient descent-based optimization methods underpin the parameter training of neural networks, and hence comprise a significant component in the impressive test results found in a number of applications. Introducing stochasticity is key to their success in practical problems, and there is some understanding of the role of stochastic gradient descent in this context. Momentum modifications of gradient descent such as Polyak’s Heavy Ball method (HB) and Nesterov’s method of accelerated gradients (NAG), are also widely adopted. In this work our focus is on understanding the role of momentum in the training of neural networks, concentrating on the common situation in which the momentum contribution is fixed at each step of the algorithm. To expose the ideas simply we work in the deterministic setting. Our approach is to derive continuous time approximations of the discrete algorithms; these continuous time approximations provide insights into the mechanisms at play within the discrete algorithms. We prove three such approximations. Firstly we show that standard implementations of fixed momentum methods approximate a time-rescaled gradient descent flow, asymptotically as the learning rate shrinks to zero; this result does not distinguish momentum methods from pure gradient descent, in the limit of vanishing learning rate. We then proceed to prove two results aimed at understanding the observed practical advantages of fixed momentum methods over gradient descent, when implemented in the non-asymptotic regime with fixed small, but non-zero, learning rate. We achieve this by proving approximations to continuous time limits in which the small but fixed learning rate appears as a parameter; this is known as the method of modified equations in the numerical analysis literature, recently rediscovered as the high resolution ODE approximation in the machine learning context. In our second result we show that the momentum method is approximated by a continuous time gradient flow, with an additional momentum-dependent second order time-derivative correction, proportional to the learning rate; this may be used to explain the stabilizing effect of momentum algorithms in their transient phase. Furthermore in a third result we show that the momentum methods admit an exponentially attractive invariant manifold on which the dynamics reduces, approximately, to a gradient flow with respect to a modified loss function, equal to the original loss function plus a small perturbation proportional to the learning rate; this small correction provides convexification of the loss function and encodes additional robustness present in momentum methods, beyond the transient phase. 

   more » « less
2. Momentum-Based Variance Reduction in Non-Convex SGD

   Cutkosky, Ashok ; Orabona, Francesco ( January 2019 , Advances in neural information processing systems)

   Wallach, H. ; Larochelle, H. ; Beygelzimer, A. ; d'Alché-Buc, F. ; Fox, E. ; Garnett, R. (Ed.)

   Variance reduction has emerged in recent years as a strong competitor to stochastic gradient descent in non-convex problems, providing the first algorithms to improve upon the converge rate of stochastic gradient descent for finding first-order critical points. However, variance reduction techniques typically require carefully tuned learning rates and willingness to use excessively large "mega-batches" in order to achieve their improved results. We present a new algorithm, STORM, that does not require any batches and makes use of adaptive learning rates, enabling simpler implementation and less hyperparameter tuning. Our technique for removing the batches uses a variant of momentum to achieve variance reduction in non-convex optimization. On smooth losses $F$, STORM finds a point $\boldsymbol{x}$ with $E[\|\nabla F(\boldsymbol{x})\|]\le O(1/\sqrt{T}+\sigma^{1/3}/T^{1/3})$ in $T$ iterations with $\sigma^2$ variance in the gradients, matching the optimal rate and without requiring knowledge of $\sigma$. 

   more » « less
3. On the Equivalence between Neural Network and Support Vector Machine

   Chen, Y. ; Huang, W. ; Nguyen, L. ; Weng, T.-W. ( December 2021 , Advances in neural information processing systems)

   Recent research shows that the dynamics of an infinitely wide neural network (NN) trained by gradient descent can be characterized by Neural Tangent Kernel (NTK) [27]. Under the squared loss, the infinite-width NN trained by gradient descent with an infinitely small learning rate is equivalent to kernel regression with NTK [4]. However, the equivalence is only known for ridge regression currently [6], while the equivalence between NN and other kernel machines (KMs), e.g. support vector machine (SVM), remains unknown. Therefore, in this work, we propose to establish the equivalence between NN and SVM, and specifically, the infinitely wide NN trained by soft margin loss and the standard soft margin SVM with NTK trained by subgradient descent. Our main theoretical results include establishing the equivalence between NN and a broad family of L2 regularized KMs with finite width bounds, which cannot be handled by prior work, and showing that every finite-width NN trained by such regularized loss functions is approximately a KM. Furthermore, we demonstrate our theory can enable three practical applications, including (i) non-vacuous generalization bound of NN via the corresponding KM; (ii) nontrivial robustness certificate for the infinite-width NN (while existing robustness verification methods would provide vacuous bounds); (iii) intrinsically more robust infinite-width NNs than those from previous kernel regression. 

   more » « less
4. Sampling with Trusthworthy Constraints: A Variational Gradient Framework

   Xingchao Liu, Xin Tong ( January 2021 , Advances in neural information processing systems)

   Sampling-based inference and learning techniques, especially Bayesian inference, provide an essential approach to handling uncertainty in machine learning (ML). As these techniques are increasingly used in daily life, it becomes essential to safeguard the ML systems with various trustworthy-related constraints, such as fairness, safety, interpretability. Mathematically, enforcing these constraints in probabilistic inference can be cast into sampling from intractable distributions subject to general nonlinear constraints, for which practical efficient algorithms are still largely missing. In this work, we propose a family of constrained sampling algorithms which generalize Langevin Dynamics (LD) and Stein Variational Gradient Descent (SVGD) to incorporate a moment constraint specified by a general nonlinear function. By exploiting the gradient flow structure of LD and SVGD, we derive two types of algorithms for handling constraints, including a primal-dual gradient approach and the constraint controlled gradient descent approach. We investigate the continuous-time mean-field limit of these algorithms and show that they have O(1/t) convergence under mild conditions. Moreover, the LD variant converges linearly assuming that a log Sobolev like inequality holds. Various numerical experiments are conducted to demonstrate the efficiency of our algorithms in trustworthy settings. 

   more » « less
5. Distributed Optimization over Time-Varying Networks: Imperfect Information with Feedback is as Good as Perfect Information

   https://doi.org/10.23919/ACC53348.2022.9867680  

   Reisizadeh, Hadi ; Touri, Behrouz ; Mohajer, Soheil ( January 2022 , 2022 American Control Conference (ACC))

   The convergence of an error-feedback algorithm is studied for decentralized stochastic gradient descent (DSGD) algorithm with compressed information sharing over time-varying graphs. It is shown that for both strongly-convex and convex cost functions, despite of imperfect information sharing, the convergence rates match those with perfect information sharing. To do so, we show that for strongly-convex loss functions, with a proper choice of a step-size, the state of each node converges to the global optimizer at the rate of O(T^{−1}). Similarly, for general convex cost functions, with a proper choice of step-size, we show that the value of loss function at a temporal average of each node’s estimates converges to the optimal value at the rate of O(T^{−1/2+ϵ }) for any ϵ > 0. 

   more » « less